Stars
Embed arbitrary modalities (images, audio, documents, etc) into large language models.
The official PyTorch implementation for arXiv'23 paper 'LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer'
{{ message }}
Embed arbitrary modalities (images, audio, documents, etc) into large language models.
The official PyTorch implementation for arXiv'23 paper 'LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer'